Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    scientific measurements

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     bump
    -0.07
    ialect
    -0.07
    .widget
    -0.07
     Nixon
    -0.07
     largest
    -0.07
    41
    -0.06
    _DENIED
    -0.06
    Best
    -0.06
    .arange
    -0.06
     nesting
    -0.06
    POSITIVE LOGITS
     _↵
    0.07
     bdsm
    0.06
     beforehand
    0.06
    ’acc
    0.06
     اصفهان
    0.06
    पत
    0.06
     rừng
    0.06
    ερό
    0.06
     во
    0.06
    :"<<
    0.06
    Act Density 0.038%

    No Known Activations